Financial Question Answering on FinQA (test)

76.05Accuracy

EEDP

Updated 1mo ago

Evaluation Results

Method	Links
EEDP 2024.02		76.05
Program-of-Thoughts (PoT) 2024.02		75.26
Chain-of-Thought (CoT) 2024.02		72.38
Program-of-Thoughts (PoT) 2024.02		68.97
Direct 2024.02		65.12
EEDP 2024.02		61.95
EEDP 2024.02		61.88
ReMem 2026.02		61.5
Ours (theory-guided context selection strategy) 2026.02		61.4
ExpRAG 2026.02		61.1
DC 2026.02		60.9
BM25 2026.02		60.4
Zero 2026.02		60.1
Chain-of-Thought (CoT) 2024.02		59.18
Ours (theory-guided context selection strategy) 2026.02		50
ExpRAG 2026.02		49.7
ReMem 2026.02		49.6
DC 2026.02		49.5
BM25 2026.02		49
Zero 2026.02		48.6
Decomposers 2024.02		46.38
TableMind++ 2026.03		45.48
Decomposers 2024.02		44.93
TableMind 2026.03		42.02
Table-R1 2026.03		41.27
Direct 2024.02		40.47
Deepseek-R1 2026.03		37.42
Qwen2.5-72B-Instruct 2026.03		35.83
Chain-of-Thought (CoT) 2024.02		35.32
EEDP 2024.02		35.05
EEDP 2024.02		34.86
Chain-of-Thought (CoT) 2024.02		34.79
Chain-of-Thought (CoT) 2024.02		34.23
Gemini-2.5-flash 2026.03		33.45
Decomposers 2024.02		32.33
EEDP 2024.02		30.47
Program-of-Thoughts (PoT) 2024.02		30.41
Direct 2024.02		30.33
Chain-of-Table 2026.03		29.47
GPT-5 2026.03		28.93
Qwen3-8B 2026.03		27.83
Tab-CoT 2026.03		27.81
Direct 2024.02		26.11
Chain-of-Thought (CoT) 2024.02		25.34
PoTable 2026.03		24.93
Direct 2024.02		22.83
Gemini-2.0-flash 2026.03		19.62
TableGPT2-7B 2026.03		17.69
Decomposers 2024.02		17.65
Program-of-Thoughts (PoT) 2024.02		15.86
TableLlama-7B 2026.03		15.73
Program-of-Thoughts (PoT) 2024.02		12.97
Decomposers 2024.02		12.34
Decomposers 2024.02		11.91
Program-of-Thoughts (PoT) 2024.02		10.56
GPT-4.1 2026.03		6.45
Direct 2024.02		1.8